Sleep–wake stage detection with single channel ECG and hybrid machine learning model in patients with obstructive sleep apnea

被引:0
|
作者
Ferda Bozkurt
Muhammed Kürşad Uçar
Cahit Bilgin
Ahmet Zengin
机构
[1] Sakarya University,Institute of Natural Sciences
[2] Sakarya University,Faculty of Engineering, Electrical
[3] Sakarya University,Electronics Engineering
[4] Sakarya University,Faculty of Medicine
来源
Physical and Engineering Sciences in Medicine | 2021年 / 44卷
关键词
Sleep–wake stage detection; Biomedical signal processing; Electrocardiography; Machine learning; Ensemble classifier;
D O I
暂无
中图分类号
学科分类号
摘要
Sleep staging is an important step in the diagnosis of obstructive sleep apnea (OSA) and this step is performed by a physician who visually scores the electroencephalography, electrooculography and electromyography signals taken by the polysomnography (PSG) device. The PSG records must be taken by a technician in a hospital environment, this may suggest a drawback. This study aims to develop a new method based on hybrid machine learning with single-channel ECG for sleep–wake detection, which is an alternative to the sleep staging procedure used in hospitals today. For this purpose, the heart rate variability signal was derived using electrocardiography (ECG) signals of 10 OSA patients. Then, QRS components in different frequency bands were obtained from the ECG signal by digital filtering. In this way, nine more signals were obtained in total. 25 features from each of the 9 signals, a total of 225 features have been extracted. Fisher feature selection algorithm and principal component analysis were used to reduce the number of features. Finally, features were classified with decision tree, support vector machines, k-nearest neighborhood algorithm and ensemble classifiers. In addition, the proposed model has been checked with the leave one out method. At the end of the study, it was shown that sleep–wake detection can be performed with 81.35% accuracy with only three features and 87.12% accuracy with 10 features. The sensitivity and specificity values for the 3 features were 0.85 and 0.77, and for 10 features the sensitivity and specificity values were 0.90 and 0.85 respectively. These results suggested that the proposed model could be used to detect sleep–wake stages during the OSA diagnostic process.
引用
收藏
页码:63 / 77
页数:14
相关论文
共 50 条
  • [1] Sleep-wake stage detection with single channel ECG and hybrid machine learning model in patients with obstructive sleep apnea
    Bozkurt, Ferda
    Ucar, Muhammed Kursad
    Bilgin, Cahit
    Zengin, Ahmet
    PHYSICAL AND ENGINEERING SCIENCES IN MEDICINE, 2021, 44 (01) : 63 - 77
  • [2] Detection of Abnormal Respiratory Events with Single Channel ECG and Hybrid Machine Learning Model in Patients with Obstructive Sleep Apnea
    Bozkurt, F.
    Ucar, M. K.
    Bozkurt, M. R.
    Bilgin, C.
    IRBM, 2020, 41 (05) : 241 - 251
  • [3] OBSTRUCTIVE SLEEP APNEA DETECTION USING ECG MORPHOLOGY AND MACHINE LEARNING
    Sayeed, Fahad
    Brooks, Justin
    Banerjee, Nilanjan
    SLEEP, 2023, 46
  • [4] Single Channel ECG for Obstructive Sleep Apnea Severity Detection Using a Deep Learning Approach
    Banluesombatkul, Nannapas
    Rakthanmanon, Thanawin
    Wilaiprasitporn, Theerawit
    PROCEEDINGS OF TENCON 2018 - 2018 IEEE REGION 10 CONFERENCE, 2018, : 2011 - 2016
  • [5] Impact of Obstructive Sleep Apnea on Sleep-Wake Stage Ratio
    Ng, Andrew Keong
    Guan, Cuntai
    2012 ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2012, : 4660 - 4663
  • [6] The sleep/wake habits of patients diagnosed as having obstructive sleep apnea
    Rosenthal, L
    Bishop, C
    Guido, P
    Syron, ML
    Helmus, T
    Rice, FM
    Roth, T
    CHEST, 1997, 111 (06) : 1494 - 1499
  • [7] Deep Learning Approaches for Early Detection of Obstructive Sleep Apnea Using Single-Channel ECG: A Systematic Literature Review
    Singh, Nivedita
    Talwekar, R. H.
    BIOMEDICAL ENGINEERING SCIENCE AND TECHNOLOGY, ICBEST 2023, 2024, 2003 : 117 - 130
  • [8] Capacitively-coupled ecg and respiration for sleep–wake prediction and risk detection in sleep apnea patients
    Huysmans, Dorien
    Castro, Ivan
    Borzée, Pascal
    Patel, Aakash
    Torfs, Tom
    Buyse, Bertien
    Testelmans, Dries
    Van Huffel, Sabine
    Varon, Carolina
    Sensors, 2021, 21 (19):
  • [9] Comprehensive Evaluation of Machine Learning Techniques for Obstructive Sleep Apnea Detection
    Sheta, Alaa
    Elashmawi, Walaa H.
    Djellal, Adel
    Braik, Malik
    Surani, Salim
    Aljahdali, Sultan
    Subramanian, Shyam
    Patel, Parth S.
    International Journal of Advanced Computer Science and Applications, 2024, 15 (12) : 104 - 116
  • [10] Development of predictive model for obstructive sleep apnea using machine learning
    Kim, H. W.
    Cho, J. W.
    Kim, D. J.
    JOURNAL OF SLEEP RESEARCH, 2020, 29 : 70 - 70